def test_compute_optimal_ranking_set(self):
ranking_set_u1 = dataset_io.RankingSet(id=dataset_io.RankingSetId(
'u1', 'Alg'),
matrix=np.array([[1, 2, 3]]),
user_ids=[1])
ranking_set_by_id = {
ranking_set_u1.id: ranking_set_u1,
}
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set_by_fold = {'u1': rating_set}
oracle = eild_oracle.EILDOracle(ranking_set_by_id, rating_set_by_fold)
distance_matrix = np.array([[0, 0.5, 0.2], [0.5, 0, 0.9],
[0.2, 0.9, 0]])
oracle.distances_by_fold = {'u1': (distance_matrix, [1, 2, 3])}
optimal_ranking_set = oracle.compute_optimal_ranking_set(
'u1', input_cutoff=3, output_cutoff=2)
self.assertEqual([1], optimal_ranking_set.user_ids)
matrix = optimal_ranking_set.matrix
self.assertEqual([2, 3], list(matrix[0, :]))
def test_compute_optimal_ranking_set(self):
ranking_set_u1 = dataset_io.RankingSet(
id=dataset_io.RankingSetId('u1', 'Alg'),
matrix=np.array([[1, 2, 3, 4], [5, 6, 7, 8]]),
user_ids=[1, 2])
ranking_set_by_id = {
ranking_set_u1.id: ranking_set_u1,
}
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set_by_fold = {'u1': rating_set}
oracle = epc_oracle.EPCOracle(ranking_set_by_id, rating_set_by_fold)
oracle.popularity_by_fold = {'u1': {
1: 1., 2: 0.25, 3: 0.5, 4: 0.75,
5: 0.8, 6: 0.3, 7: 0.6, 8: 0.01
}}
optimal_ranking_set = oracle.compute_optimal_ranking_set(
'u1', input_cutoff=4, output_cutoff=3)
self.assertEqual([1, 2], optimal_ranking_set.user_ids)
matrix = optimal_ranking_set.matrix
self.assertEqual([2, 3, 4], list(matrix[0, :]))
self.assertEqual([8, 6, 7], list(matrix[1, :]))
def setUp(self):
super().setUp()
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set.test = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set_by_fold = {'u1': rating_set}
self.eild = eild.EILD(ranking_set_by_id={},
rating_set_by_fold=rating_set_by_fold)
def test_computes_likers(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[(1, 2, 5), (2, 2, 5), (2, 3, 5), (3, 3, 5)])
rating_set_by_fold = {'u1': rating_set}
likers_by_fold = rating_utils._compute_likers_by_fold(rating_set_by_fold)
self.assertIn('u1', likers_by_fold)
likers_by_item_id = likers_by_fold['u1']
self.assertDictEqual({2: {1, 2}, 3: {2, 3}}, likers_by_item_id)
def test_ignores_test_and_validation(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set.test = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(2, 3, 5)])
rating_set.validation = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(1, 3, 5)])
rating_set_by_fold = {'u1': rating_set}
likers_by_fold = rating_utils._compute_likers_by_fold(rating_set_by_fold)
self.assertIn('u1', likers_by_fold)
likers_by_item_id = likers_by_fold['u1']
self.assertDictEqual({}, likers_by_item_id)
def test_compute_popularity(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[
(1, 1, 5),
(1, 2, 5),
(2, 1, 5),
(2, 3, 5),
])
rating_set_by_fold = {'u1': rating_set}
expected_popularity = {(1, 1.), (2, 0.5), (3, 0.5)}
popularity = set(rating_utils._compute_popularity(rating_set).items())
self.assertEqual(expected_popularity, popularity)
def test_computes_distances(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[(1, 2, 5), (2, 2, 5), (4, 2, 5), (2, 3, 5), (3, 3, 5), (4, 3, 5)])
rating_set_by_fold = {'u1': rating_set}
distance_by_fold = rating_utils.compute_distances_by_fold(rating_set_by_fold)
self.assertIn('u1', distance_by_fold)
distance_matrix, item_ids = distance_by_fold['u1']
expected_matrix = np.array([[0., 1/3], [1/3, 0.]])
error_matrix = np.abs(distance_matrix - expected_matrix)
are_almost_equal = (error_matrix < 1e-8).all()
self.assertTrue(are_almost_equal)
self.assertSequenceEqual([2, 3], item_ids)
def test_ignores_test_and_validation(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[])
rating_set.test = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(2, 3, 5)])
rating_set.validation = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(1, 3, 5)])
rating_set_by_fold = {'u1': rating_set}
distance_by_fold = rating_utils.compute_distances_by_fold(rating_set_by_fold)
self.assertIn('u1', distance_by_fold)
distance_matrix, item_ids = distance_by_fold['u1']
expected_matrix = np.array([])
are_almost_equal = ((distance_matrix - expected_matrix) < 1e-8).all()
self.assertTrue(are_almost_equal)
self.assertSequenceEqual([], item_ids)
def test_compute_rated_by_fold(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[
(1, 1, 5),
(1, 2, 5),
(2, 1, 5),
(2, 3, 5),
])
rating_set_by_fold = {'u1': rating_set}
rated_by_fold = rating_utils.compute_rated_by_fold(
rating_set_by_fold, split_name='base')
self.assertIn('u1', rated_by_fold)
rated = rated_by_fold['u1']
expected_rated = {1: {1, 2}, 2: {1, 3}}
self.assertDictEqual(expected_rated, rated)
def test_compute_optimal_ranking_set(self):
ranking_set_u1 = dataset_io.RankingSet(id=dataset_io.RankingSetId(
'u1', 'Alg'),
matrix=np.array([[1, 2, 3, 4],
[5, 6, 7, 8]]),
user_ids=[1, 2])
ranking_set_by_id = {
ranking_set_u1.id: ranking_set_u1,
}
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(4, 1, 5)])
rating_set.test = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[
(1, 3, 5),
(1, 2, 5),
(2, 1, 5),
(2, 8, 5),
])
rating_set_by_fold = {'u1': rating_set}
oracle = map_oracle.MAPOracle(ranking_set_by_id, rating_set_by_fold)
optimal_ranking_set = oracle.compute_optimal_ranking_set(
'u1', input_cutoff=4, output_cutoff=3)
self.assertEqual([1, 2], optimal_ranking_set.user_ids)
matrix = optimal_ranking_set.matrix
self.assertEqual(3, len(matrix[0, :]))
self.assertSetEqual({2, 3}, set(matrix[0, 0:2]))
self.assertTrue(set(matrix[0, 2:]).issubset({1, 4}))
self.assertEqual(3, len(matrix[1, :]))
self.assertSetEqual({8}, set(matrix[1, 0:1]))
self.assertTrue(set(matrix[1, 1:]).issubset({5, 6, 7}))
def test_compute_hits_by_fold(self):
rating_set = dataset_io.RatingSet(fold='u1')
rating_set.base = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'], data=[(4, 1, 5)])
rating_set.test = pd.DataFrame.from_records(
columns=['user_id', 'item_id', 'rating'],
data=[
(1, 1, 5),
(1, 2, 5),
(2, 1, 5),
(2, 3, 5),
])
rating_set_by_fold = {'u1': rating_set}
hits_by_fold = rating_utils.compute_hits_by_fold(rating_set_by_fold)
self.assertIn('u1', hits_by_fold)
hits = hits_by_fold['u1']
expected_hits = {1: {1, 2}, 2: {1, 3}}
self.assertDictEqual(expected_hits, hits)